BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:How physical systems can learn by themselves: Kirk Lecture - Andre
 a Liu (University of Pennsylvania)
DTSTART:20231101T160000Z
DTEND:20231101T170000Z
UID:TALK205684@talks.cam.ac.uk
DESCRIPTION:In order for artificial neural networks to learn a task\, one 
 must solve an inverse design problem. What network will produce the desire
 d output? We have harnessed AI approaches to design physical systems to pe
 rform functions inspired by biology. But artificial neural networks requir
 e a computer in order to learn in top-down fashion by minimizing a cost fu
 nction. By contrast\, the brain learns bottom up on its own\, with each ne
 uron adjusting itself and its synapses without knowing what all the other 
 neurons are doing\, and without the aid of an external computer. We have i
 ntroduced an approach to bottom-up learning that has been realized in phys
 ical systems that learn on their own.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR